© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12946
    Prev
    Next
    INDEX
    Explanations

    mentions of metro areas or regions in news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of metropolitan areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.82
    IENT
    -0.77
    IGHTS
    -0.73
    nir
    -0.71
     Qiao
    -0.71
    ivation
    -0.70
    CLASSIFIED
    -0.70
    etts
    -0.68
    ENGTH
    -0.68
    emption
    -0.66
    POSITIVE LOGITS
    plex
    0.87
     tracts
    0.86
     metro
    0.84
    ropolitan
    0.84
     blackout
    0.77
     tract
    0.74
     area
    0.74
     drain
    0.72
     outlet
    0.71
     metropolitan
    0.71
    Activations Density 0.007%

    No Known Activations